adr-check

Run ADR conformance checks, explain failures, and identify required ADR/doc updates for the current change.

1.74x

Quality

79%

Does it follow best practices?

Impact

96%

1.74x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/adr-check/SKILL.md

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a tight, executable workflow with clear sequencing, validation feedback loops, and no padding. It is an excellent example of a concise single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient, assuming Claude's competence with no over-explanation of ADR concepts; every line earns its place.	5 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands (git diff, the adr_guard.py invocations) covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequence with explicit validation checkpoints and a feedback loop (fast guard fails -> fix -> re-run, then final CI profile), matching the rubric's exemplar.	5 / 5
Progressive Disclosure	A simple, well-organized skill under 50 lines with no need for external references; sections (## Steps, ## Output) are clearly structured, which suffices for a top score.	5 / 5
	Total	20 / 20 Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and clearly conveys the skill's purpose and actions, but it omits an explicit 'Use when...' trigger clause and lacks keyword synonyms, limiting trigger discovery and completeness.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios (e.g., changes touching architecture, guardrails, or shared contracts).

Include synonyms and natural user phrasing such as 'architecture decision records' alongside 'ADR'.

Optionally enumerate the concrete check categories to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the ADR domain and three concrete actions ('Run ADR conformance checks, explain failures, and identify required ADR/doc updates'), but does not enumerate the specific check categories, so it falls short of comprehensive (5).	4 / 5
Completeness	It clearly answers 'what' (run checks, explain failures, identify doc updates) but provides no explicit 'when/Use when...' trigger clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	'ADR' is a relevant natural keyword, but the description lacks common variations/synonyms (e.g., 'architecture decision records') and natural user phrasing.	3 / 5
Distinctiveness Conflict Risk	The ADR-conformance niche is specific and mostly distinct, with only minor overlap risk against general code-review or docs skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: PaloAltoNetworks/shifter
Path: .claude/skills/adr-check/SKILL.md
Commit: c46caa4

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.